About the job
About the Role
Join us at root as we revolutionize software security with our pioneering autonomous AI platform. Our technology automatically identifies, rectifies, and validates software vulnerabilities, performing these tasks end-to-end and at scale. Imagine AI agents that seamlessly update dependencies, modify Dockerfiles, rebuild Go binaries with patched versions, and validate everything autonomously. This is an intellectually challenging and highly technical role where you will design, implement, and scale AI agent systems for real-world codebases. You will be at the confluence of backend engineering, AI systems, and application security, crafting agents, context pipelines, and evaluation frameworks that enable autonomous reasoning in production environments.
What You’ll Do
- Design and develop AI agents from the ground up to autonomously detect, repair, and validate vulnerable components.
- Establish and maintain scalable infrastructure for agent operations [AIOps], focusing on context management, evaluations, and orchestration.
- Create collaborative workflows that empower multiple agents to work together and reason collectively.
- Build tools and utilities that enhance agent capabilities (e.g., image inspection, diff generation, static analysis).
- Implement evaluation and performance metrics to ensure agent reliability and accuracy.
- Develop hybrid and vector database applications for efficient retrieval and context management.
- Integrate AI applications such as MCP-based systems, chat interfaces, and standalone utilities.
- Ensure all experiments are instrumented with tracing, observability, and structured metrics for reproducibility.
